Unified resource capacity management

Abstract

Systems and techniques for unified resource capacity data management are described herein. An aggregate shift duration, a number of shifts, and an aggregate downtime duration within a specific calendar period may be determined, using a machine learning model, for each resource of a plurality of resources. A scheduling available capacity may be generated for the plurality of resources using the determined aggregate shift duration, the number of shifts, and the aggregate downtime duration. A planning available capacity may be generated using the scheduling available capacity and a retrieved efficiency factor. An optimal resource allocation may be calculated based on the planning available capacity and a customer demand. An indication that the set of training data was updated based on the optimal resource allocation may be received. The planning available capacity for each resource of the plurality of resources may be updated based on the updated set of training data.

What is claimed is: 
     
         1 . A system comprising:
 a storage device, comprising a data store to host data provided from a unified resource capacity data management;   at least one processor; and   memory including instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:   receive a set of training data from the data store, the set of training data including data for a plurality of resources and a customer demand;   train a machine learning model using the received set of training data;   determine, using the machine learning model, an aggregate shift duration, a number of shifts, and an aggregate downtime duration for each resource of the plurality of resources within a specific calendar period based on the set of training data, the plurality of resources including at least one critical resource and at least one non-critical resource;   generate, using the at least one processor, a scheduling available capacity during the specific calendar period for the plurality of resources using the aggregate shift duration, the number of shifts, and the aggregate downtime duration;   receive an efficiency factor for the unified resource capacity data management from the data store;   generate a planning available capacity using the scheduling available capacity and the efficiency factor;   calculate, using the machine learning model, an optimal resource allocation based on the planning available capacity and the customer demand;   display, on a display of a computing device, the optimal resource allocation;   receive an indication via the computing device that the set of training data was updated based on the optimal resource allocation; and   update, using the machine learning model, the planning available capacity for each resource of the plurality of resources based on the updated set of training data.   
     
     
         2 . The system of  claim 1 , the memory further comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:
 automatically identify a change in the set of training data for a resource of the plurality of resources; and   update the planning available capacity for the resource of the plurality of resources.   
     
     
         3 . The system of  claim 1 , wherein the planning available capacity is generated only for the at least one critical resource of the plurality of resources. 
     
     
         4 . The system of  claim 1 , wherein the specific calendar period includes at least one of a day, a week, a month, or a year. 
     
     
         5 . The system of  claim 1 , wherein the aggregate shift duration and aggregate downtime duration are calculated in hours. 
     
     
         6 . The system of  claim 1 , wherein the efficiency factor is based in part on an aggregate changeover time and an aggregate maintenance time during the specific calendar period. 
     
     
         7 . The system of  claim 1 , the memory further comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:
 calculate, using the machine learning model, an aggregate scheduling available capacity for the plurality of resources; and   generate a second planning available capacity using the aggregate scheduling available capacity and the efficiency factor.   
     
     
         8 . The system of  claim 1 , the memory further comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:
 retrieve, from the data store, an inventory of units produced for the specific calendar period;   calculate, using the machine learning model, a throughput rate based on the inventory of units produced and a time availability, the time availability based on the aggregate shift duration, the number of shifts, and the specific calendar period; and   generate a third planning available capacity using the throughput rate and the time availability for the plurality of resources.   
     
     
         9 . At least one non-transitory machine-readable medium comprising instructions for a unified resource capacity data management, which when executed by processing circuitry, cause the processing circuitry to perform operations to:
 retrieve a set of training data from a data store, the set of training data including data for a plurality of resources and a customer demand;   train a machine learning model using the retrieved set of training data;   determine, using the machine learning model, an aggregate shift duration, a number of shifts, and an aggregate downtime duration for each resource of the plurality of resources within a specific calendar period based on the set of training data, the plurality of resources including at least one critical resource and at least one non-critical resource;   generate, using the processing circuitry, a scheduling available capacity during the specific calendar period for the plurality of resources using the aggregate shift duration, the number of shifts, and the aggregate downtime duration;   retrieve an efficiency factor for the unified resource capacity data management from the data store;   generate a planning available capacity using the scheduling available capacity and the efficiency factor;   calculate, using the machine learning model, an optimal resource allocation based on the planning available capacity and the customer demand;   display, on a display of a computing device, the optimal resource allocation;   receive an indication via the computing device that the set of training data was updated based on the optimal resource allocation; and   update, using the machine learning model, the planning available capacity for each resource of the plurality of resources based on the updated set of training data.   
     
     
         10 . The at least one non-transitory machine-readable medium of  claim 9 , further comprising instructions that, when executed by the processing circuitry, cause the processing circuitry to perform operations to:
 automatically identify a change in the set of training data for a resource of the plurality of resources; and   update the planning available capacity for the resource of the plurality of resources.   
     
     
         11 . The at least one non-transitory machine-readable medium of  claim 9 , wherein the planning available capacity is generated only for the at least one critical resource of the plurality of resources. 
     
     
         12 . The at least one non-transitory machine-readable medium of  claim 9 , wherein the specific calendar period includes at least one of a day, a week, a month, or a year. 
     
     
         13 . The at least one non-transitory machine-readable medium of  claim 9 , wherein the aggregate shift duration and aggregate downtime duration are calculated in hours. 
     
     
         14 . The at least one non-transitory machine-readable medium of  claim 9 , wherein the efficiency factor is based in part on an aggregate changeover time and an aggregate maintenance time during the specific calendar period. 
     
     
         15 . The at least one non-transitory machine-readable medium of  claim 9 , further comprising instructions that, when executed by the processing circuitry, cause the processing circuitry to perform operations to:
 calculate, using the machine learning model, an aggregate scheduling available capacity for the plurality of resources; and   generate a second planning available capacity using the aggregate scheduling available capacity and the efficiency factor.   
     
     
         16 . The at least one non-transitory machine-readable medium of  claim 9 , further comprising instructions that, when executed by the processing circuitry, cause the processing circuitry to perform operations to:
 retrieve, from the data store, an inventory of units produced for the specific calendar period;   calculate, using the machine learning model, a throughput rate based on the inventory of units produced and a time availability, the time availability based on the aggregate shift duration, the number of shifts, and the specific calendar period; and   generate a third planning available capacity using the throughput rate and the time availability for the plurality of resources.   
     
     
         17 . A method for a unified resource capacity data management, the method comprising:
 retrieving a set of training data from a data store, the set of training data including data for a plurality of resources and a customer demand;   training a machine learning model using the retrieved set of training data;   determining, using the machine learning model, an aggregate shift duration, a number of shifts, and an aggregate downtime duration for each resource of the plurality of resources within a specific calendar period based on the set of training data, the plurality of resources including at least one critical resource and at least one non-critical resource;   generating a scheduling available capacity during the specific calendar period for the plurality of resources using the aggregate shift duration, the number of shifts, and the aggregate downtime duration;   retrieving an efficiency factor for the unified resource capacity data management from the data store;   generating a planning available capacity using the scheduling available capacity and the efficiency factor;   calculating, using the machine learning model, an optimal resource allocation based on the planning available capacity and the customer demand;   displaying, on a display of a computing device, the optimal resource allocation;   receiving an indication via the computing device that the set of training data was updated based on the optimal resource allocation; and   updating, using the machine learning model, the planning available capacity for each resource of the plurality of resources based on the updated set of training data.   
     
     
         18 . The method of  claim 17 , further comprising:
 automatically identifying a change in the set of training data for a resource of the plurality of resources; and   updating the planning available capacity for the resource of the plurality of resources.   
     
     
         19 . The method of  claim 17 , wherein the planning available capacity is generated only for the at least one critical resource of the plurality of resources. 
     
     
         20 . The method of  claim 17 , wherein the specific calendar period includes at least one of a day, a week, a month, or a year. 
     
     
         21 . The method of  claim 17 , wherein the aggregate shift duration and aggregate downtime duration are calculated in hours. 
     
     
         22 . The method of  claim 17 , wherein the efficiency factor is based in part on an aggregate changeover time and an aggregate maintenance time during the specific calendar period. 
     
     
         23 . The method of  claim 17 , further comprising:
 calculating, using the machine learning model, an aggregate scheduling available capacity for the plurality of resources; and   generating a second planning available capacity using the aggregate scheduling available capacity and the efficiency factor.   
     
     
         24 . The method of  claim 17 , further comprising:
 retrieving, from the data store, an inventory of units produced for the specific calendar period;   calculating, using the machine learning model, a throughput rate based on the inventory of units produced and a time availability, the time availability based on the aggregate shift duration, the number of shifts, and the specific calendar period; and   generating a third planning available capacity using the throughput rate and the time availability for the plurality of resources.